Multivariate Determination of Glucose in Whole Blood Using Partial Least-Squares and Artificial Neural Networks Based on Mid-Infrared Spectroscopy

The infrared (IR) spectra of whole blood EDTA samples, in the range between 1500 and 750 cm−1, obtained from the patient population of a general hospital, were used to compare different multivariate calibration techniques for quantitative glucose determination. Ninety-six spectra of whole undiluted blood samples with glucose concentration ranging between 44 and 291 mg/dL were used to create calibration models based on a combination of partial least-squares (PLS) and artificial neural network (ANN) methods. The prediction capabilities of these calibration models were evaluated by comparing their standard errors of prediction (SEP) with those obtained with the use of PLS and principal component regression (PCR) calibration models in an independent prediction set consisting of 31 blood samples. The optimal model based on the combined PLS-ANN produced smaller SEP values (15.6 mg/dL) compared with those produced with the use of either PLS (21.5 mg/dL) or PCR (24.0 mg/dL) methods. Our results revealed that the combined PLS-ANN models can better approximate the deviations from linearity in the relationship between spectral data and concentration, compared with either PLS or PCR models.

[1]  R. Landgraf,et al.  Blood Glucose Measurement by Infrared Spectroscopy , 1989, The International journal of artificial organs.

[2]  H. M. Heise,et al.  Calibration modeling by partial least-squares and principal component regression and its optimization using an improved leverage correction for prediction testing , 1990 .

[3]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[4]  P. Gemperline,et al.  Spectroscopic calibration and quantitation using artificial neural networks , 1990 .

[5]  H. H. Thodberg,et al.  Optimal minimal neural interpretation of spectra , 1992 .

[6]  T. Næs,et al.  Locally weighted regression and scatter correction for near-infrared reflectance data , 1990 .

[7]  E. V. Thomas,et al.  Partial least-squares methods for spectral analyses. 1. Relation to other quantitative calibration methods and the extraction of qualitative information , 1988 .

[8]  H. M. Heise,et al.  Multivariate determination of glucose in whole blood by attenuated total reflection infrared spectroscopy , 1989 .

[9]  W. M. Doyle Absorbance Linearity and Repeatability in Cylindrical Internal Reflectance FT-IR Spectroscopy of Liquids , 1990 .

[10]  Yitzhak Mendelson,et al.  Carbon dioxide laser based multiple ATR technique for measuring glucose in aqueous solutions. , 1988, Applied optics.

[11]  Paul J. Gemperline,et al.  Nonlinear multivariate calibration using principal components regression and artificial neural networks , 1991 .

[12]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[13]  E. V. Thomas,et al.  Noninvasive glucose monitoring in diabetic patients: a preliminary evaluation. , 1992, Clinical chemistry.

[14]  B. Kowalski,et al.  Numerical and statistical properties of target factor analysis methods , 1989 .

[15]  H. M. Heise,et al.  On the efficiency of algorithms for multivariate linear calibration used in analytical spectroscopy , 1992 .

[16]  E. Braue,et al.  Consistency in Circle Cell FT-IR Analysis of Aqueous Solutions , 1987 .

[17]  J D Kruse-Jarres,et al.  Multivariate calibration for assays in clinical chemistry using attenuated total reflection infrared spectra of human blood plasma. , 1989, Analytical chemistry.

[18]  Yitzhak Mendelson,et al.  Glucose determination in simulated plasma solutions using infrared spectrophotometry , 1992, 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  M. Schaldach,et al.  Quantitative ATR spectroscopy: some basic considerations. , 1981, Applied optics.

[20]  David M. Haaland,et al.  Post-Prandial Blood Glucose Determination by Quantitative Mid-Infrared Spectroscopy , 1992 .

[21]  M A Arnold,et al.  Determination of physiological levels of glucose in an aqueous matrix with digitally filtered Fourier transform near-infrared spectra. , 1990, Analytical chemistry.

[22]  B.-C. Lin,et al.  Blood glucose measurement by multiple attenuated total reflection and infrared absorption spectroscopy , 1990, IEEE Transactions on Biomedical Engineering.

[23]  J. W. Hall,et al.  Near-infrared spectrophotometry: a new dimension in clinical chemistry. , 1992, Clinical chemistry.

[24]  David M. Haaland,et al.  Reagentless Near-Infrared Determination of Glucose in Whole Blood Using Multivariate Calibration , 1992 .

[25]  Multivariate calibration of glucose in blood by PLS using spectral and fourier-domain data , 1990 .

[26]  A. J. Collins,et al.  Introduction To Multivariate Analysis , 1981 .